[1L3-GS-10] AI application: Behavioral economics

[1L3-GS-10-05] Using Supply Chain Network Information and High-Frequency Mobility Datato Forecast Firm Dynamics

〇Rui Kato¹, Daisuke Miyakawa², Masaki Yanaoka³, Shinji Yukimoto¹ (1. Sumitomo Mitsui Finance and Leasing Co., Ltd., 2. Waseda University, 3. Tokyo Shoko Research, Ltd.)

Keywords:Alternative Data, GPS Data, Credit Demand, Supply Chain Network

In this paper, we use individual-level GPS location data, which has been increasingly used in recent years, to measure the size of factory-level population and forecast leasing demand of the “transaction partners” of the companies for which the population is measured. First, we use GPS location data to measure changes in the population at the main factories of companies in the manufacturing industry. Second, using such measured data and the lease contract data, we construct a machine learning-based prediction model of leasing demand at the suppliers of the company. Except for the periods when corporate activities were greatly disturbed by the Covid-19 pandemic, the employment of the GPS location data improves the prediction power of the leasing demand.